Parallelization of synthetic events with genetic surprisal data representing a genetic sequence of an organism

A method of parallelization of creating synthetic events with genetic surprisal data representing a genetic sequence of an organism comprising:

• a computer retrieving data records of patients to be searched for synthetic events;
• the computer receiving a plurality of synthetic events and associated metadata from a user, wherein the metadata comprises at least one genetic surprisal data attribute;
• and
• the computer dividing the plurality of synthetic events into single synthetic events and assigning the single synthetic event and associated synthetic event metadata to one of the plurality of computer processing elements;
• within each processing element:
• searching data records of patients for genetic surprisal data and storing matches of the data records in a repository;
• generating a cluster comprising a centroid by populating the cluster based on all of the matches of the data records;
• calculating a new centroid for each cluster;
• calculating a Euclidean distance in multiple dimensions for each match of data records to the new centroid for each cluster;
• reassigning each match of data to the new centroid of each cluster based on the shortest calculated Euclidean distance to the new centroid for each cluster;
• determining at least two cohorts, a control cohort and a treatment cohort, from the clusters, and based on the associated metadata from the user and storing the at least two cohorts in a repository;
• and
• retrieving any other data based on the associated metadata of the synthetic event and combining the other data retrieved with the at least two cohorts to form a synthetic event and storing the synthetic event in the repository.

A computer program product for parallelization of updating synthetic events with genetic surprisal data representing a genetic sequence of an organism comprising:

• one or more computer-readable, tangible storage devices;
• program instructions, stored on at least one of the one or more storage devices, to receive a synthetic event and associated metadata from a user, wherein the metadata comprises at least one genetic surprisal data attribute;
• program instructions, stored on at least one of the one or more storage devices, to divide the synthetic event into cohort parts and assign the cohort parts and associated synthetic event metadata to one of the plurality of computer processing elements;
• and
• within each processing element, program instructions, stored on at least one of the one or more storage devices, to:
• search data records of patients for genetic surprisal data and store matches of the data records in a repository;
• generate a cluster comprising a centroid by populating the cluster based on all of the matches of the data records;
• calculate a new centroid for each cluster;
• calculate a Euclidean distance in multiple dimensions for each match of data records to the new centroid for each cluster;
• reassign each match of data to the new centroid of each cluster based on the shortest calculated Euclidean distance to the new centroid for each cluster;
• and
• determine at least one cohort part, a control cohort or a treatment cohort, from the clusters, and based on the associated metadata from the user and store the at least one cohort part in a repository;
• program instructions, stored on at least one of the one or more storage devices, to retrieve the cohort parts from the repository and recombine the cohort parts into updated synthetic events based on the metadata and store the updated synthetic events in the repository.

A computer program product for parallelization of creating synthetic events with genetic surprisal data representing a genetic sequence of an organism comprising:

• program instructions, stored on at least one of the one or more storage devices, to retrieve data records of patients to be searched for synthetic events;
• program instructions, stored on at least one of the one or more storage devices, to receive a plurality of synthetic events and associated metadata from a user, wherein the metadata comprises at least one genetic surprisal data attribute;
• and
• program instructions, stored on at least one of the one or more storage devices, to divide the plurality of synthetic events into single synthetic events and assign the single synthetic event and associated synthetic event metadata to one of the plurality of computer processing elements;
• within each processing element, program instructions, stored on at least one of the one or more storage devices, to:
• search data records of patients for genetic surprisal data and store matches of the data records in a repository;
• generate a cluster comprising a centroid by populating the cluster based on all of the matches of the data records;
• calculate a new centroid for each cluster;
• calculate a Euclidean distance in multiple dimensions for each match of data records to the new centroid for each cluster;
• reassign each match of data to the new centroid of each cluster based on the shortest calculated Euclidean distance to the new centroid for each cluster;
• determine at least two cohorts, a control cohort and a treatment cohort, from the clusters, and based on the associated metadata from the user and store the at least two cohorts in a repository;
• and
• retrieve any other data based on the associated metadata of the synthetic event and combine the other data retrieved with the at least two cohorts to form a synthetic event and store the synthetic event in the repository.

A system for parallelization of updating synthetic events with genetic surprisal data representing a genetic sequence of an organism comprising:

• one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices;
• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to receive a synthetic event and associated metadata from a user, wherein the metadata comprises at least one genetic surprisal data attribute;
• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to divide the synthetic event into cohort parts and assign the cohort parts and associated synthetic event metadata to one of the plurality of computer processing elements;
• and
• within each processing element, program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to:
• search data records of patients for genetic surprisal data and store matches of the data records in a repository;
• generate a cluster comprising a centroid by populating the cluster based on all of the matches of the data records;
• calculate a new centroid for each cluster;
• calculate a Euclidean distance in multiple dimensions for each match of data records to the new centroid for each cluster;
• reassign each match of data to the new centroid of each cluster based on the shortest calculated Euclidean distance to the new centroid for each cluster;
• and
• determine at least one cohort part, a control cohort or a treatment cohort, from the clusters, and based on the associated metadata from the user and store the at least one cohort part in a repository;
• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to retrieve the cohort parts from the repository and recombine the cohort parts into updated synthetic events based on the metadata and store the updated synthetic events in the repository.

A system for parallelization of creating synthetic events with genetic surprisal data representing a genetic sequence of an organism comprising:

• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to retrieve data records of patients to be searched for synthetic events;
• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to receive a plurality of synthetic events and associated metadata from a user, wherein the metadata comprises at least one genetic surprisal data attribute;
• and
• program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to divide the plurality of synthetic events into single synthetic events and assign the single synthetic event and associated synthetic event metadata to one of the plurality of computer processing elements;
• within each processing element, program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, to:
• search data records of patients for genetic surprisal data and store matches of the data records in a repository;
• generate a cluster comprising a centroid by populating the cluster based on all of the matches of the data records;
• calculate a new centroid for each cluster;
• calculate a Euclidean distance in multiple dimensions for each match of data records to the new centroid for each cluster;
• reassign each match of data to the new centroid of each cluster based on the shortest calculated Euclidean distance to the new centroid for each cluster;
• determine at least two cohorts, a control cohort and a treatment cohort, from the clusters, and based on the associated metadata from the user and store the at least two cohorts in a repository;
• and
• retrieve any other data based on the associated metadata of the synthetic event and combine the other data retrieved with the at least two cohorts to form a synthetic event and store the synthetic event in the repository.